Naslov
Improved Image Quality Measure Through Particle Swarm Optimization

Autori
Dumić, Emil ; Grgić, Sonja ; Grgić, Mislav

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
PROCEEDINGS IWSSIP 2011 / Zovko-Cihlar, Branka ; Behlilović, Narcis ; Hadžialić, Mesud - Sarajevo : Faculty of Electrical Engineering, University of Sarajevo, 2011, 167-172

ISBN
978-9958-9966-1-0

Skup
18th International Conference on Systems, Signals and Image Processing, IWSSIP 2011

Mjesto i datum
Sarajevo, Bosna i Hercegovina, 16.06.2011. - 18.06.2011

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Discrete Wavelet Transform; MSE; PSNR; VIF; VSNR; SSIM; MSSIM; Image Quality Measure; DMOS

Sažetak
In this paper we present new approach to the objective image quality evaluation based on discrete wavelet transform (DWT) and particle swarm optimization (PSO). DWT was applied on image difference (difference between original and degraded image) that is decomposed into approximation and detail subbands. DWT coefficients were computed using Coiflet wavelet filter banks. The coefficients were used to compute new image quality measure (IQM) that is defined as perceptual weighted difference between coefficients of original and degraded image. Weighting factors for wavelet subbands have been experimentally determined using PSO optimization algorithm to achieve the best possible correlation with results of subjective (perceptual) image quality evaluation. Experimental results demonstrate that the proposed technique has high correlation with results of subjective test and low computational time important for real-time applications.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo

POVEZANOST RADA